Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

21

ICML
2006
IEEE

favoriteEmaildiscussreport

256views Machine Learning» more ICML 2006»

Automatic basis function construction for approximate dynamic programming and reinforcement learning

13 years 10 months ago

Automatic basis function construction for approximate dynamic programming and reinforcement learning

Download www.ece.mcgill.ca

We address the problem of automatically constructing basis functions for linear approximation of the value function of a Markov Decision Process (MDP). Our work builds on results by Bertsekas and Casta˜non (1989) who proposed a method for automatically aggregating states to speed up value iteration. We propose to use neighborhood component analysis (Goldberger et al., 2005), a dimensionality reduction technique created for supervised learning, in order to map a high-dimensional state space to a lowdimensional space, based on the Bellman error, or on the temporal difference (TD) error. We then place basis function in the lower-dimensional space. These are added as new features for the linear function approximator. This approach is applied to a high-dimensional inventory control problem.

Philipp W. Keller, Shie Mannor, Doina Precup

Real-time Traffic

Basis Function | ICML 2006 | Machine Learning | Markov Decision Process | Value Function |

claim paper

Related Content

» Basis Function Construction in Reinforcement Learning Using CascadeCorrelation Learning Ar...

» Basis function construction for hierarchical reinforcement learning

» Constructing action set from basis functions for reinforcement learning of robot control

» Improving reinforcement learning function approximators via neuroevolution

» Learning Basis Functions in Hybrid Domains

» Generalization in Reinforcement Learning Safely Approximating the Value Function

» A Convergent Reinforcement Learning Algorithm in the Continuous Case The FiniteElement Rei...

» Modelbased function approximation in reinforcement learning

» Transfer of task representation in reinforcement learning using policybased protovalue fun...

Post Info
More Details (n/a)

Added	13 Jun 2010
Updated	13 Jun 2010
Type	Conference
Year	2006
Where	ICML
Authors	Philipp W. Keller, Shie Mannor, Doina Precup

Comments (0)